Page 520 - Kaleidoscope Academic Conference Proceedings 2024

Poster Session 4
P4.1 Modified CNN Model for Hand Gesture Recognition Using Sign Language
Abhishek Kumar Mishra and Rajesh Kumar Singh (IFTM University, Moradabad, India)

In recent years, convolutional neural networks have become the most effective method in image
classification. Generally communication people in our daily life is by speaking with

voice but some communications can possible with hand gesture in this study static hand gesture
can be used as a non-verbal communication techniques utilized in sign language is the hand
gesture. It is now mostly used by deaf and dumb individuals to communicate with other people or
among themselves when they have hearing or speech issues. It was suggested in this paper to use
CNN with data augmentation to recognize static hand gestures. The MNIST Sign Language
Dataset has been enhanced with dynamic learning rate parameters using the CNN model. The
model was tested on 7172 images after being trained on 27,455 images. The accuracy of the
model using supplemented data was 99.76%, which is nearly greater than the accuracy of the
CNN model without augmentation (86.87%).
P4.2 Privacy, Human Rights, and Web 3.0

Danyella Johnston, Gyu Myoung Lee, Sorren Hanvey and Aine MacDermott (Liverpool John
Moores University, United Kingdom (Great Britain))

Technology and our networked environment has made privacy an increasingly challenging state
to achieve but in order to ensure we continue to meet the foundational standard for human rights,
it is essential that privacy is elevated as a priority global discussion. We must continually review
whether technology and network deliverables are meeting a privacy standard in a format that is
accessible to all. In this paper we review whether Web 2.0 has met the required standard and if
not, what impact this has had on society. From this we then ask what we need to address in Web
3.0 to ensure those inadequacies do not proliferate into Web 3.0 developments. Finally, this paper
offers a set of five human rights centric privacy design principles for future development.

P4.3 Revitalising Agriculture in South 24 Parganas: Strategies for Sustainable Farming and Direct Sales

Utsab Bhowmick (Uluberia Government Polytechnic, India); Pritam Majhi (AICTE, Uluberia
Government Polytechnic, India & Technical Edu. & Training, India); Shriya Goswami (Uluberia
Govt. Polytechnic & AICTE, India)

The paper delves into the multifaceted challenges confronting farmers in West Bengal's South 24
Parganas

region, encompassing issues such as inadequate financial support, limited technical knowledge,
unsustainable practices, overproduction, market price fluctuations, and unmet needs for basic
facilities and amenities. These challenges have collectively contributed to a decline in farming
interest and an uptick in land sales among the farming community. Our study is dedicated to
proposing effective strategies aimed at empowering farmers, bolstering financial viability, and
fostering community development, achieved through meticulous surveys and interviews. A
notable contribution of our research lies in the development of a mobile application that
streamlines direct interactions between sellers and buyers. This innovative app boasts user profiles,
a recommendation system for personalized product discovery, and a language-agnostic chat
feature that facilitates real-time translations, ensuring seamless communication and efficient deal
closure.

– 476 –